> For AI agents: the complete documentation index is available at /llms.txt, the full documentation bundle is available at /llms-full.txt.

# Model Selection Guide

This guide introduces the models supported by Midscene, two ways to connect them, and when to use one Default model or combine multiple models.

## Supported models

Midscene supports these multimodal models for operating user interfaces: [Doubao Seed](/model-api-setup.md#doubao-seed-model), [Qwen](/model-api-setup.md#qwen), [DeepSeek](/model-api-setup.md#deepseek), [Google Gemini](/model-api-setup.md#gemini), [OpenAI GPT](/model-api-setup.md#gpt), [Moonshot Kimi](/model-api-setup.md#kimi), [Xiaomi MiMo](/model-api-setup.md#xiaomi-mimo), [Zhipu GLM-V](/model-api-setup.md#glm-v), [Ant Ling](/model-api-setup.md#ant-ling), and [Jev (experimental)](/model-api-setup.md#jev), as well as the other compatible models [AutoGLM](/model-api-setup.md#auto-glm) and [UI-TARS](/model-api-setup.md#ui-tars).

## Choose a connection method

Midscene supports two ways to connect a model. Choose either one:

- **Model API key**: Use an API key from a model provider to connect to the models listed above. See [Use a model API key](/model-api-setup.md).
- **ChatGPT subscription**: Sign in and authorize Midscene to call GPT models using your ChatGPT subscription. Available models depend on your account. See [Use a ChatGPT subscription](/chatgpt-subscription.md).

## Start with one Default model

Configure one multimodal Default model for planning, localization, and insight. This works for most scenarios. See [Use a model API key](/model-api-setup.md) for supported models and configuration examples, or choose [Use a ChatGPT subscription](/chatgpt-subscription.md).

## Use multi-model capabilities to handle complex scenarios {#multi-model-strategy}

Midscene supports combining multiple models to handle complex scenarios. A single automation task may require multi-step planning, precise element localization, and data extraction or result evaluation. Different models have different strengths across these capabilities.

Keep the Default model and add Planning, Locate, or Insight models to divide the work according to those strengths within the same task. For example, use a stronger planning model for long workflows with conditional branches, a localization model for difficult UI targets, or an insight model for complex assertions and structured data extraction.

Configure each role independently; you do not need to add every specialized model at once. Any role without a dedicated model continues to use the Default model:

| Model          | Responsibility                                                                                       |
| -------------- | ---------------------------------------------------------------------------------------------------- |
| Default model  | Required base configuration providing all capabilities; any role without a specialized model uses it |
| Planning model | Planning for complex goals, multiple steps, and branching scenarios                                  |
| Locate model   | Independent element localization, including action targets and `deepLocate`                          |
| Insight model  | Data extraction, assertions, and page understanding                                                  |

Combining models can increase latency and token usage. Use [Model advanced configuration and debugging](/model-config.md#verify-model-connectivity) to identify the problem, then [configure multiple models](/model-config.md#multi-model-combination-example) as needed.